Papers by Renaud Lecoeuche
Focus tracking in dialogs
Assisted multi-modal dialogue
Focus tracking in dialogs
Interactive tools for controlling requirements elicitation are normally driven by rules of specif... more Interactive tools for controlling requirements elicitation are normally driven by rules of specification construction, rather than by conventions of human dialogue. On the other hand, theories of dialogue tend to ignore the interaction with constraints imposed by the domain of application. Various competing theories of dialogue exist but there have been few comparative studies of their use in nontrivial tasks. This paper presents a comparative study of the use of focus theories for requirements elicitation which required us to be precise about our interpretation of our chosen focus theories and to develop an innovative means of empirical testing for them.
Evaluation gives a precise evaluation of the approach proposed in the thesis. It also deals with ... more Evaluation gives a precise evaluation of the approach proposed in the thesis. It also deals with the development method we used to build our system. It consits of chapters 9 and 10. Conclusion concludes the thesis and discusses issues left for further research. It consists of chapter 11. 1.3. ORGANISATION Describe global and local focus theories based on different aspects such as domain structure, dialogue intentions, and semantic relations, • Describe applications making use of the notion of focus.
Dialog component re-use in recognition systems
International Journal of Human-Computer Studies, 2000
Interactive reasoning tools are usually driven by an agenda of tasks to perform, rather than by c... more Interactive reasoning tools are usually driven by an agenda of tasks to perform, rather than by conventions of human dialogue. On the other hand, theories of dialogue in natural language tend to ignore the constraints imposed by reasoning tools. This paper presents a system composed of a reasoning module and a dialogue manager which cooperate to produce dialogues that are suitable for reasoning and follow human dialogue conventions. The dialogue manager is driven by focus rules. Various competing focus theories exist but there have been few comparative studies of their use in non-trivial tasks. We make a comparative study of the use of focus theories, which requires us to be precise about our interpretation of our chosen focus theories, and to develop an innovative means of empirical testing for them. We evaluate the theories on an example of combined dialogue and reasoning from the domain of requirements elicitation.
The Knowledge Engineering Review, 1999
In recent years, the capabilities of knowledge-based systems to communicate with their users have... more In recent years, the capabilities of knowledge-based systems to communicate with their users have evolved from simple interactions to complex dialogues. With this evolution comes a need to understand what makes a good dialogue. In this paper, we are concerned with dialogue coherence. We review the notion of focus, which partly explains this property, and its use for user-system communication. First, we examine the major theories dealing with this notion. We describe what their contribution is and how they differ. Then, we illustrate the benefits of using the notion of focus and especially the improvement in text coherence. We pay particular attention to how the notion can concretely be implemented. Its integration with other techniques and theories is described. We conclude the paper by pointing out remaining issues in the understanding of the notion of focus. The contribution of this paper is to provide a classification of the theories of focus and to show the improvements they off...
Requirements engineering is a complex task which benefits from computer support. Despite the prog... more Requirements engineering is a complex task which benefits from computer support. Despite the progress made in automatic reasoning on requirements, the tools supporting requirements elicitation remain difficult to use. In this paper we propose a novel approach where a tool's reasoning is intimately linked to the dialogue it has with its users. Because the dialogue is guided by rules ensuring coherence, the interaction with the tool is more natural. We discuss in detail the rules we use to organise the dialogue and how we apply them to the requirements elicitation tool. We present an evaluation of this approach demonstrating improvements in usability during the elicitation process.
Developing dialogue systems is a complex process. In particular, designing efficient dialogue man... more Developing dialogue systems is a complex process. In particular, designing efficient dialogue management strategies is often difficult as there are no precise guidelines to develop them and no sure test to validate them. Several suggestions have been made recently to use reinforcement learning to search for the optimal management strategy for specific dialogue situations. These approaches have produced interesting results, including applications involving real world dialogue systems. However, reinforcement learning suffers from the fact that it is state based. In other words, the optimal strategy is expressed as a decision table specifying which action to take in each specific state. It is therefore difficult to see whether there is any generality across states. This limits the analysis of the optimal strategy and its potential for re-use in other dialogue situations. In this paper we tackle this problem by learning rules that generalize the state-based strategy. These rules are mor...
Naacl, 2001
Developing dialogue systems is a complex process. In particular, designing efficient dialogue man... more Developing dialogue systems is a complex process. In particular, designing efficient dialogue management strategies is often difficult as there are no precise guidelines to develop them and no sure test to validate them. Several suggestions have been made recently to use reinforcement learning to search for the optimal management strategy for specific dialogue situations. These approaches have produced interesting results, including applications involving real world dialogue systems. However, reinforcement learning suffers from the fact that it is state based. In other words, the optimal strategy is expressed as a decision table specifying which action to take in each specific state. It is therefore difficult to see whether there is any generality across states. This limits the analysis of the optimal strategy and its potential for re-use in other dialogue situations. In this paper we tackle this problem by learning rules that generalize the state-based strategy. These rules are more readable than the underlying strategy and therefore easier to explain and re-use. We also investigate the capability of these rules in directing the search for the optimal strategy by looking for generalization whilst the search proceeds.
Using Focus Rules in Requirements Elicitation Dialogues
Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, 1999
Page 1. Using Focus Rules in Requirements Elicitation Dialogues Renaud Lecceuche *+ and Dave Robe... more Page 1. Using Focus Rules in Requirements Elicitation Dialogues Renaud Lecceuche *+ and Dave Robertson* and Catherine Barry* ... [Lecoeuche et al., 1998] Renaud Lecoeuche, Chris Mellish, Catherine Barry, and Dave Robertson. User-system dia ...
Mixed initiative interface control
Assisted multi-modal dialogue
Focus tracking in dialogs
Development framework for mixing semantics-driven and state-driven dialog
Formalisation et evaluation des theories traitant des centres d'attention et application aux dialogues en langue naturelle d'acquisition des besoins
Http Www Theses Fr, 1999
Interactive human-machine interface with a plurality of active states, storing user input in a node of a multinode token
Web server controls for web enabled recognition and/or audible prompting for call controls
Uploads
Papers by Renaud Lecoeuche